Paper Citation Record · LEDGER

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation

As of 10 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 0 inbound Pith citation observations for arXiv:2607.14586.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2607.14586 v1

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T01:41:52.473153Z

measured 37 of 37 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

37 of 37 outbound references displayed

verified exact0
verified fuzzy0
unresolved37
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 18a3fdb3-4f74-4a0e-acdd-06fce3c33428 · outbound

This paper cites HM3D- OVON: A dataset and benchmark for open-vocabulary object goal navigation,.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation HM3D- OVON: A dataset and benchmark for open-vocabulary object goal navigation,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:48.500807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9b56fb0-b2b5-417e-b0a8-d256ce72b834 · outbound

This paper cites GOAT-Bench: A benchmark for multi-modal lifelong navigation,.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation GOAT-Bench: A benchmark for multi-modal lifelong navigation,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:48.673352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eadc8c0c-5395-45cd-9797-00c5b107faed · outbound

This paper cites Task-oriented Sequential Grounding and Navigation in 3D Scenes.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation Task-oriented Sequential Grounding and Navigation in 3D Scenes

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:48.849680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0f17fa7-441f-42a7-a952-368e7d833415 · outbound

This paper cites Object goal navigation using goal-oriented semantic exploration,.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation Object goal navigation using goal-oriented semantic exploration,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:49.022785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c796ac1-d23e-45b0-b045-ec58a7283cb8 · outbound

This paper cites VLFM: Vision-language frontier maps for zero- shot semantic navigation,.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation VLFM: Vision-language frontier maps for zero- shot semantic navigation,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:49.144127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a067809-8a12-46ae-aa37-5bb25bb21965 · outbound

This paper cites Move to understand a 3D scene: Bridging visual ground- ing and exploration for efficient and versatile embodied navigation,.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation Move to understand a 3D scene: Bridging visual ground- ing and exploration for efficient and versatile embodied navigation,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:49.291227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50a43686-fe47-4752-9f7b-62aac0e018f3 · outbound

This paper cites Unifying 3D vision-language understanding via prompt- able queries,.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation Unifying 3D vision-language understanding via prompt- able queries,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:49.436063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d527683-1a5e-4d70-b51b-fc4b5c3fe068 · outbound

This paper cites NavGPT: Explicit reasoning in vision- and-language navigation with large language models,.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation NavGPT: Explicit reasoning in vision- and-language navigation with large language models,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:49.573559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5aa67a84-1514-45aa-b566-4eae579fd2a3 · outbound

This paper cites NaVid: Video-based VLM plans the next step for vision-and-language navigation,.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation NaVid: Video-based VLM plans the next step for vision-and-language navigation,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:49.701297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dce93dd5-08cb-4fd7-8c8e-71b966f293d7 · outbound

This paper cites L3MVN: Leveraging large language models for visual target navigation,.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation L3MVN: Leveraging large language models for visual target navigation,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:49.873639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69f1c1d8-2f6f-4429-a47c-f4ca7c899a6a · outbound

This paper cites SayNav: Grounding large language models for dynamic planning to navigation in new environments,.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation SayNav: Grounding large language models for dynamic planning to navigation in new environments,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:50.039088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 892e9a91-5e9e-48ad-8e2b-d1d3b5a24d47 · outbound

This paper cites SG-Nav: Online 3D scene graph prompting for LLM-based zero-shot object navigation,.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation SG-Nav: Online 3D scene graph prompting for LLM-based zero-shot object navigation,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:50.157628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79a23742-38c4-4ea3-91ac-b217f9128ac8 · outbound

This paper cites A frontier-based approach for autonomous exploration,.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation A frontier-based approach for autonomous exploration,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:50.256336Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc107c30-578f-49fe-ac81-c41f2db81e81 · outbound

This paper cites PONI: Potential functions for ObjectGoal navigation with interaction-free learning,.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation PONI: Potential functions for ObjectGoal navigation with interaction-free learning,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:50.349270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da2cbd47-b561-478a-b215-033197827d8c · outbound

This paper cites PIRLNav: Pre- training with imitation and RL finetuning for ObjectNav,.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation PIRLNav: Pre- training with imitation and RL finetuning for ObjectNav,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:50.444445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09e1a243-b281-4ec8-b3e7-5648140213bb · outbound

This paper cites Uni-NaVid: A video-based vision-language-action model for unifying embodied navigation tasks,.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation Uni-NaVid: A video-based vision-language-action model for unifying embodied navigation tasks,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:50.542590Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a3d1d78-6de2-4ea9-ab8d-aa01ba6f415d · outbound

This paper cites V oroNav: V oronoi-based zero-shot object navigation with large language model,.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation V oroNav: V oronoi-based zero-shot object navigation with large language model,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:50.628115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 802f9793-758c-4bf7-977d-bc16ec2717fb · outbound

This paper cites MapGPT: Map-guided prompting with adaptive path planning for vision-and-language navigation,.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation MapGPT: Map-guided prompting with adaptive path planning for vision-and-language navigation,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:50.724452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 498b2f0e-96c6-4f64-a22a-dc8358fbb9a0 · outbound

This paper cites ESC: Exploration with soft commonsense constraints for zero-shot object navigation,.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation ESC: Exploration with soft commonsense constraints for zero-shot object navigation,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:50.790386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24574323-eae1-4655-80a9-1195d1452786 · outbound

This paper cites Flamingo: A visual language model for few-shot learning,.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation Flamingo: A visual language model for few-shot learning,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:50.867928Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e2fba9b-0600-4a47-887f-d57a4a4582dd · outbound

This paper cites Visual instruction tuning,.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation Visual instruction tuning,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:50.920017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c8710cb-484d-441d-8c36-40d5c00b95ea · outbound

This paper cites BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models,.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:51.006655Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b29a0332-5521-4879-b866-2c8ecbf728ad · outbound

This paper cites 3D-LLM: Injecting the 3D world into large language models,.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation 3D-LLM: Injecting the 3D world into large language models,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:51.065132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08cbdb82-3867-4f6f-b8e6-85aead536ee5 · outbound

This paper cites An embodied generalist agent in 3D world,.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation An embodied generalist agent in 3D world,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:51.157750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e34d34f8-d4b2-4fb4-af0b-4e5b6366163d · outbound

This paper cites LL3DA: Visual interactive instruction tuning for omni- 3D understanding,.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation LL3DA: Visual interactive instruction tuning for omni- 3D understanding,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:51.255377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9487fa09-aa21-4e69-8356-ece45640f4d8 · outbound

This paper cites EmbodiedGPT: Vision-language pre-training via em- bodied chain of thought,.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation EmbodiedGPT: Vision-language pre-training via em- bodied chain of thought,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:51.351345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 384b949d-474e-4ee8-aa98-4e388da0437a · outbound

This paper cites Dynam3D: Dynamic layered 3D tokens empower VLM for vision-and-language navigation,.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation Dynam3D: Dynamic layered 3D tokens empower VLM for vision-and-language navigation,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:51.444318Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac9517b3-6973-40af-8537-4165a3d72d82 · outbound

This paper cites AstraNav-Memory: Contexts compression for long memory,.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation AstraNav-Memory: Contexts compression for long memory,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:51.535275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 396570cb-60cd-49dc-b30b-6293bab5e135 · outbound

This paper cites DINOv3.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation DINOv3

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:51.639055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 091fa90e-0c94-4c79-a71b-30384284b95c · outbound

This paper cites Qwen2.5-VL Technical Report.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation Qwen2.5-VL Technical Report

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:51.731349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eee35148-b0bf-4a26-ba8a-f59e8a7f2822 · outbound

This paper cites LoRA: Low-rank adaptation of large language models,.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation LoRA: Low-rank adaptation of large language models,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:51.859604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d1a3746-65ce-4bce-a4be-876c4a5f6a2d · outbound

This paper cites Habitat: A platform for embodied AI research,.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation Habitat: A platform for embodied AI research,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:51.952688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc49ba36-6586-4ca4-96c2-dfda73da8a48 · outbound

This paper cites The design of stretch: A compact, lightweight mobile manipulator for indoor human environments,.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation The design of stretch: A compact, lightweight mobile manipulator for indoor human environments,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:52.050418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e48a6d5-2dde-493f-9901-72f9c75493a3 · outbound

This paper cites TANGO: Training- free embodied AI agents for open-world tasks,.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation TANGO: Training- free embodied AI agents for open-world tasks,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:52.146704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e30485e-cbee-4082-a043-3c7a8f232d83 · outbound

This paper cites MSGNav: Unleashing the power of multi-modal 3D scene graph for zero-shot embodied navigation,.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation MSGNav: Unleashing the power of multi-modal 3D scene graph for zero-shot embodied navigation,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:52.243259Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f91037b-3f67-4718-8b22-302b24b279ee · outbound

This paper cites Cows on pasture: Baselines and benchmarks for language-driven zero-shot object navigation,.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation Cows on pasture: Baselines and benchmarks for language-driven zero-shot object navigation,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:52.342874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24499448-6823-4f3b-a2b8-66be4601a539 · outbound

This paper cites Embodied VideoAgent: Persistent memory from ego- centric videos and embodied sensors enables dynamic scene under- standing,.

SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation Embodied VideoAgent: Persistent memory from ego- centric videos and embodied sensors enables dynamic scene under- standing,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-02T01:41:52.473153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.